Related papers: An optical-lensing inspired data thinning method f…
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and…
By obtaining photometric redshift information, tomography allows us to cross-correlate galaxy ellipticities in different source redshift bins. The cross-correlation is non-vanishing because the different bins share much of the foreground…
This paper describes an inverse analysis method using neural networks on optical spectroscopy, and its application to the quantitative optical constant evaluation. The present method consists of three subprocesses. First, measurable…
We present a novel, domain-agnostic, model-independent, unsupervised, and universally applicable Machine Learning approach for dimensionality reduction based on the principles of algorithmic complexity. Specifically, but without loss of…
Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…
Large-sample data became prevalent as data acquisition became cheaper and easier. While a large sample size has theoretical advantages for many statistical methods, it presents computational challenges. Sketching, or compression, is a…
Photon-photon interactions are an essential requirement of quantum photonic information processing. One way to generate these interactions is to utilize an atom strongly coupled to an optical cavity. This system exhibits the photon blockade…
Dataset Condensation aims to condense a large dataset into a smaller one while maintaining its ability to train a well-performing model, thus reducing the storage cost and training effort in deep learning applications. However, conventional…
We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then obtain the…
Datasets for object detection often do not account for enough variety of glasses, due to their transparent and reflective properties. Specifically, open-vocabulary object detectors, widely used in embodied robotic agents, fail to…
We explore the effectiveness of deep learning convolutional neural networks (CNNs) for estimating strong gravitational lens mass model parameters. We have investigated a number of practicalities faced when modelling real image data, such as…
Deep neural networks, when optimized with sufficient data, provide accurate representations of high-dimensional functions; in contrast, function approximation techniques that have predominated in scientific computing do not scale well with…
Optical neural networks are emerging as a powerful and versatile tool for processing optical signals directly in the optical domain with superior speed, integrability, and functionality. Their application to optical polarization enables…
Compressed sensing is an image reconstruction technique to achieve high-quality results from limited amount of data. In order to achieve this, it utilizes prior knowledge about the samples that shall be reconstructed. Focusing on image…
With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising problem of low-dose computed tomography using deep learning. Although low-dose computed…
Thermal Images profile the passive radiation of objects and capture them in grayscale images. Such images have a very different distribution of data compared to optical colored images. We present here a work that produces a grayscale…
We review a new systematic data analysis procedure for color transparency experiments and its application to the proton nucleus scattering experiment. The method extracts the hard scattering rate as well as the survival probability for the…
Photomosaic images are a type of images consisting of various tiny images. A complete form can be seen clearly by viewing it from a long distance. Small tiny images which replace blocks of the original image can be seen clearly by viewing…
Most camera lens systems are designed in isolation, separately from downstream computer vision methods. Recently, joint optimization approaches that design lenses alongside other components of the image acquisition and processing pipeline…
One of the main challenges in modeling massive stars to the onset of core collapse is the computational bottleneck of nucleosynthesis during advanced burning stages. The number of isotopes formed requires solving a large set of…